让AI协作更可靠：用户自定义规则，保障AI不干扰人、反而补短板。
Multi-Round Human-AI Collaboration with User-Specified Requirements
- 用户自定义规则定义AI不应伤害人类优势，且在人类易错处提供互补帮助。
- 算法在非平稳环境下仍能控制错误率，实测提升人类诊断准确率。
- 适合高风险决策场景，如医疗、司法，需可解释可控的多轮人机协作。
随着人类在高风险决策中越来越多依赖多轮对话式AI，亟需可靠框架确保交互真正提升判断质量。本文从以人为本视角出发，提出两个核心原则：反事实损害（counterfactual harm）——确保AI不会削弱人类优势；互补性（complementarity）——确保AI在人类易出错环节提供有效补充。通过用户定义规则的形式化表达，将具体任务中的“损害”与“互补”含义明确化。进而设计一种无需分布假设的在线算法，具备有限样本保证，可强制执行用户设定的约束。在两个交互场景中评估：大模型模拟医学诊断协作，以及人类众包进行图像推理任务。结果表明，该在线方法即使在动态变化的交互环境中，也能维持预设的反事实损害和互补性违规率。进一步发现，收紧或放宽约束会带来可预测的人类准确率变化，验证了两原则作为实际调控杠杆的有效性，无需建模或限制人类行为即可优化多轮协作决策质量。
原文摘要 · Abstract (English)
As humans increasingly rely on multiround conversational AI for high stakes decisions, principled frameworks are needed to ensure such interactions reliably improve decision quality. We adopt a human centric view governed by two principles: counterfactual harm, ensuring the AI does not undermine human strengths, and complementarity, ensuring it adds value where the human is prone to err. We formalize these concepts via user defined rules, allowing users to specify exactly what harm and complementarity mean for their specific task. We then introduce an online, distribution free algorithm with finite sample guarantees that enforces the user-specified constraints over the collaboration dynamics. We evaluate our framework across two interactive settings: LLM simulated collaboration on a medical diagnostic task and a human crowdsourcing study on a pictorial reasoning task. We show that our online procedure maintains prescribed counterfactual harm and complementarity violation rates even under nonstationary interaction dynamics. Moreover, tightening or loosening these constraints produces predictable shifts in downstream human accuracy, confirming that the two principles serve as practical levers for steering multi-round collaboration toward better decision quality without the need to model or constrain human behavior.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。